Communication method and apparatus
By registering the AI model and generating unified identification, the problem of inconsistent understanding between different devices by access network equipment training is solved, and the application effect and management convenience of the AI model are improved.
Patent Information
- Application Number
- PCT/CN2024/081854
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-12
- Filing Date
- 2024-03-15
- Publication Date
- 2024-11-21
AI Technical Summary
In AI model application scenarios, the AI model trained by access network devices does not have a unified understanding, which affects its use effect and increases the difficulty of collaborative work between devices.
Provide a communication method and device, by registering the AI model, generating a unified identification, so that the terminal device, access network device and network management network element can understand the AI model uniformly, and after the model registration is completed, the terminal device is moving. The model can still be called using this identity when reaching other coverage areas, for easy detection and management.
It improves the effectiveness of AI models in AI application scenarios, ensures consistency in AI models understanding among devices, facilitates subsequent management and detection, and reduces signaling overhead.
Smart Images

Figure CN2024081854_21112024_PF_FP_ABST
Abstract
Description
Communication method and device
[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on May 12, 2023, with application number 202310539530.2 and invention name “A Communication Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The present application relates to the field of communications, and more particularly, to a communication method and apparatus. Background Art
[0003] With the advancement of data storage and computing capabilities, artificial intelligence (AI) technology is increasingly being used. AI can be applied to communications systems such as new radio (NR) systems, improving network performance and user experience through intelligent data collection and analysis.
[0004] The 3rd Generation Partnership Project (3GPP) has introduced multiple AI application scenarios, in which all or part of the AI functions are implemented by terminal devices in some AI application scenarios. Therefore, in one possible AI model transmission method, the access network device trains the AI model and transmits the AI model to the terminal device. However, since the AI model is trained by the access network device, the various devices involved in the application scenario of the first model, such as network management network elements, terminal devices, and access network devices, do not have a unified understanding of the AI model, which affects the use effect of the AI model in the AI application scenario.
[0005] Summary of the Invention
[0006] The present application provides a communication method and apparatus for registering an AI model.
[0007] In a first aspect, a communication method is provided, applied to a first network device. The method can be executed by the first network device, or by a component (e.g., a chip or circuit) of the first network device, without limitation. For ease of description, the following description uses execution by the first network device as an example.
[0008] The method may include: training to obtain a first model; sending a first request message, the first request message is used to request registration of the first model, the first request message includes a first identifier, and the first identifier corresponds to the first model.
[0009] Exemplarily, the first network device in the present application may be an access network device, and the first model may include an AI model.
[0010] It should be understood that in this application, there is no order for obtaining the first model and sending the first request information. The first network device may send the first request information after training to obtain the first model, or it may send the first request information before the model training is completed after determining the training requirements of the first model. This application does not limit this.
[0011] In the above technical solution, by registering the first model and corresponding the first identifier and the first model, various devices involved in the application scenario of the first model, such as terminal devices, access network devices, and network management network elements within the coverage of the same operator, can have a unified understanding of the first model, including that after registration is completed, each device can use the first identifier to call the first model. Furthermore, when the terminal device moves to the coverage of other access network devices, it can still use the first identifier to call the first model, which facilitates subsequent detection and management of the first model, thereby improving the application effect of the first model.
[0012] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: obtaining first information, the first information including at least one model identifier, the at least one model identifier being a model identifier that can be registered by the first network device; and assigning a first identifier to the first model based on the first information.
[0013] Based on the above solution, the first network device can select one from the model identifiers in the first information as the identifier of the first model, so that the first network device can assign an identifier to the first model more flexibly.
[0014] In combination with the first aspect, in some implementations of the first aspect, obtaining the first information includes: receiving the first information from the second network device; or pre-configuring the first information in the first network device.
[0015] Exemplarily, that the first network device is pre-configured with the first information may include that the first network device is pre-configured with the first information in factory settings.
[0016] In combination with the first aspect, in some implementations of the first aspect, obtaining the first information includes: a first network device generating the first information.
[0017] Illustratively, the first network device may generate the first information according to the training requirements of the first model.
[0018] In combination with the first aspect, in certain implementations of the first aspect, the first information also includes at least one of the following: auxiliary information of the model corresponding to at least one model identifier, cell information that can use the model corresponding to at least one model identifier, information on the effective time of the model corresponding to at least one model identifier, and terminal device information that can use the model corresponding to at least one model identifier.
[0019] Among them, the auxiliary information of the model may include at least one of the following: the input information of the model, the output information of the model, the version number corresponding to the model, the format of the model, the model's requirements for terminal device capabilities, the equipment vendor identification to which the model can be applied, the scenarios in which the model can be used, the use case of the model, the complexity of the model calculation, the model processing capability requirements, the range of the model data volume, the accuracy of the model, and the function of the model.
[0020] Based on the above solution, by adding relevant information about the model corresponding to the model identifier to the first information, the first network device can more accurately and quickly determine the identifier assigned to the first model.
[0021] In combination with the first aspect, in certain implementations of the first aspect, the first request information also includes at least one of the following: auxiliary information of the first model, a list of terminal devices that can use the first model, a list of cells that can use the first model, a list of public land mobile networks that can use the first model, the expected time of using the first model, an index for indicating the first model, and a mapping relationship for mapping the first model.
[0022] Among them, the auxiliary information refers to the above description of the auxiliary information of the model. It should be understood that the auxiliary information of the first model and the auxiliary information of the model corresponding to at least one model identifier may include the same content or different content, and this application does not limit this.
[0023] Based on the above solution, by adding relevant information about the first model to the first request message, a more comprehensive description of the first model can be achieved, which is beneficial for improving the efficiency and accuracy of first model registration. In addition, including an index used to indicate the first model and / or a mapping relationship used to map the first model in the first request message can avoid the need to send a complete model identifier when subsequently indicating the model between the first network device and the second network device, thereby reducing signaling overhead.
[0024] In combination with the first aspect, in some implementations of the first aspect, sending the first request information includes: sending indication information to the terminal device, the indication information including the first request information, to instruct the terminal device to forward the first request information to the second network device.
[0025] Furthermore, the method may also include: receiving a registration result of the first model from the terminal device, wherein the registration result of the first model is sent to the terminal device by the second network device.
[0026] Specifically, the registration result of the first model may be indicated to the terminal device explicitly or implicitly by the second network device.
[0027] Exemplarily, the second network device sends feedback information to the terminal device, where the feedback information includes information indicating whether the registration is successful or failed.
[0028] Exemplarily, the terminal device starts a timer after sending the first request information to the second network device. If no feedback is received from the second network device within a certain period of time, it indicates that the registration is successful.
[0029] Exemplarily, the second network device may further instruct the terminal device to forward the registration result of the first model to the first network device.
[0030] In combination with the first aspect, in some implementations of the first aspect, sending the first request information includes: sending the first request information to the second network device.
[0031] In combination with the first aspect, in some implementations of the first aspect, the method may further include: receiving a registration result of the first model from the second network device.
[0032] The registration result of the first model can be explicitly or implicitly indicated to the first network device by the second network device. The sending method of the registration result of the first model refers to the above-mentioned method of the second network device sending the registration result of the first model to the terminal device, which is not repeated here.
[0033] It should be understood that if the first request information is forwarded by the terminal device to the second network device, the second network device can also directly feedback the registration result of the first model to the first network device. At this time, the terminal device can indicate the first network device to the second network device when sending the first request information. Exemplarily, the terminal device also sends the identifier of the first network device when sending the first request information.
[0034] In combination with the first aspect, in some implementations of the first aspect, if the registration result is successful registration, the method further includes: sending second information to the terminal device, where the second information includes the first model.
[0035] In combination with the first aspect, in certain implementations of the first aspect, the second information also includes at least one of the following: a first identifier, indication information that the first model has completed registration, auxiliary information of the first model, an index corresponding to the first identifier, an index corresponding to the first identifier and an applicable cell range, a mapping rule corresponding to the first identifier, a mapping rule corresponding to the first identifier and an applicable cell range.
[0036] Among them, the first identifier can be indicated by an index or mapping relationship, and then the first model can be indicated, which avoids the need to send the complete first identifier when the terminal device and the first network device subsequently indicate the first model, thereby reducing signaling overhead.
[0037] In combination with the first aspect, in certain implementations of the first aspect, if the registration result is registration failure, the method further includes: sending a second request information based on the training requirements of the modified first model.
[0038] In combination with the first aspect, in certain implementations of the first aspect, the first network device includes a centralized unit and a distributed unit, and the method also includes: the centralized unit assigns a model identifier to the distributed unit based on the model identifier already assigned on the distributed unit and / or the distributed unit's demand information for the model identifier and sends it to the distributed unit.
[0039] Based on the above solution, the centralized unit and the distributed units interact with each other regarding the demand for pre-allocated model identifiers under the separation architecture, and the centralized unit collects the demands of each distributed unit, thereby ensuring the model identifier allocation requirements of the entire first network device. For example, it can ensure that the distributed units obtain sufficient model identifiers, avoid one model corresponding to multiple model identifiers, and avoid multiple distributed units requiring the same model identifier.
[0040] For example, if the number of model identifiers required by a distributed unit exceeds the number of model identifiers pre-allocated on the distributed unit, the centralized unit may allocate model identifiers that can be released by other distributed units or the centralized unit itself to the distributed unit.
[0041] For example, if multiple distributed units require the same model identifier, the centralized unit may allocate the model identifier to one of the distributed units and indicate to the other distributed units that the model identifier has been allocated.
[0042] For example, if the distributed units require different model identifiers for the same model, the centralized unit may unify the model identifiers of the model.
[0043] In combination with the first aspect, in some implementations of the first aspect, the first request information further includes: a unit identifier, where the unit identifier is used to identify a centralized unit or a distributed unit for training the first model.
[0044] Based on the above solution, the centralized unit or distributed unit for training the first model can be determined through the unit identification, making the registration result more reliable.
[0045] In combination with the first aspect, in some implementations of the first aspect, the first network device includes a centralized unit and a distributed unit, and the method further includes: if the first model is a model trained by the centralized unit, the centralized unit sends the second information to the terminal device through the distributed unit; if the first model is a model trained by the distributed unit, the distributed unit sends the second information to the terminal device, or the distributed unit sends the first model to the centralized unit, and the centralized unit sends the second information to the terminal device through the distributed unit.
[0046] In a second aspect, a communication method is provided, applied to a terminal device. The method can be executed by the terminal device, or by a component of the terminal device (e.g., a chip or circuit), without limitation. For ease of description, the following description uses execution by a terminal device as an example.
[0047] The method may include: receiving indication information from a first network device, the indication information including first request information, the indication information being used to instruct the terminal device to forward the first request information to a second network device, the first request information being used to request registration of a first model, the first request information including a first identifier, the first identifier corresponding to the first model, and the first model being a model trained by the first network device; and forwarding the first request information to the second network device.
[0048] In combination with the second aspect, in some implementations of the second aspect, the method further includes: receiving a registration result of the first model from the second network device and forwarding the result to the first network device.
[0049] In combination with the second aspect, in certain implementations of the second aspect, the first request information also includes at least one of the following: auxiliary information of the first model, a list of terminal devices that can use the first model, a list of cells that can use the first model, a list of public land mobile networks that can use the first model, the expected time of using the first model, an index for indicating the first model, and a mapping relationship for mapping the first model.
[0050] In combination with the second aspect, in some implementations of the second aspect, the method further includes: receiving second information from the first network device, where the second information includes the first model.
[0051] In combination with the second aspect, in certain implementations of the second aspect, the second information also includes at least one of the following: a first identifier, indication information that the first model has completed registration, auxiliary information of the first model, an index corresponding to the first identifier, an index corresponding to the first identifier and an applicable cell range, a mapping rule corresponding to the first identifier, a mapping rule corresponding to the first identifier and an applicable cell range.
[0052] In a third aspect, a communication method is provided, applied to a second network device. The method can be executed by the second network device, or by a component (e.g., a chip or circuit) of the second network device, without limitation. For ease of description, the following description uses execution by the second network device as an example.
[0053] The method may include: receiving first request information, the first request information is used to request registration of a first model, the first request information includes a first identifier, the first identifier corresponds to the first model, and the first model is a model trained by a first network device; registering the first model based on the first request information.
[0054] Exemplarily, the second network device may be a core network device or an operations, administration and maintenance (OAM) device.
[0055] In combination with the third aspect, in certain implementations of the third aspect, receiving the first request information includes: receiving the first request information from the first network device; or receiving the first request information from the terminal device, the first request information is sent by the terminal device after receiving the indication information from the first network device, and the indication information includes the first request information.
[0056] In combination with the third aspect, in some implementations of the third aspect, the method also includes: sending the registration result of the first model to the first network device based on the first request information from the first network device; or sending the registration result of the first model to the terminal device based on the first request information from the terminal device.
[0057] It should be understood that the beneficial effects of the second and third aspects can be found in the description of the first aspect.
[0058] In a fourth aspect, a communication device is provided, including: a processing unit for training and obtaining a first model; a transceiver unit for sending a first request message, wherein the first request message is used to request registration of the first model, and the first request message includes a first identifier, and the first identifier corresponds to the first model.
[0059] The transceiver unit can perform the reception and transmission processing in the aforementioned first aspect, and the processing unit can perform other processing except reception and transmission in the aforementioned first aspect.
[0060] In the fifth aspect, a communication device is provided, including: a transceiver unit for receiving indication information from a first network device, wherein the indication information includes first request information, the indication information is used to instruct the terminal device to forward the first request information to the second network device, the first request information is used to request registration of a first model, the first request information includes a first identifier, the first identifier corresponds to the first model, and the first model is a model trained by the first network device; the transceiver unit is also used to forward the first request information to the second network device.
[0061] Optionally, the communication apparatus further includes a processing unit. For example, the processing unit is configured to determine, based on the indication information, whether to forward the first request message to the second network device.
[0062] The transceiver unit can perform the reception and transmission processing in the aforementioned second aspect, and the processing unit can perform other processing except reception and transmission in the aforementioned second aspect.
[0063] In the sixth aspect, a communication device is provided, including: a transceiver unit for receiving a first request message, the first request message is used to request registration of a first model, the first request message includes a first identifier, the first identifier corresponds to the first model, and the first model is a model trained by the first network device; a processing unit for registering the first model based on the first request information.
[0064] The transceiver unit can perform the receiving and sending processing in the aforementioned third aspect, and the processing unit can perform other processing except receiving and sending in the aforementioned third aspect.
[0065] In a seventh aspect, a communication device is provided, comprising a processor, wherein the processor is configured to call and run the computer program from a memory, so that the communication device executes the method in any possible implementation of the first to third aspects above.
[0066] Optionally, there are one or more processors.
[0067] Optionally, the communication device further includes one or more memories, and the memories may be integrated with the processor, or the memories may be provided separately from the processor.
[0068] Optionally, the communication device further includes a transmitter (transmitter) and a receiver (receiver).
[0069] In an eighth aspect, a communication system is provided, comprising a first network device and a second network device, wherein the first network device is used to execute the method in any possible implementation of the first aspect, and the second network device is used to execute the method in any possible implementation of the third aspect.
[0070] In combination with the eighth aspect, in certain implementations of the eighth aspect, the communication system further includes a terminal device, which is used to execute the method in any possible implementation of the second aspect above.
[0071] In the ninth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program or code, and when the computer program or code is run on a computer, the computer executes the method in any possible implementation of the first to third aspects above.
[0072] In the tenth aspect, a chip is provided, comprising at least one processor, wherein the at least one processor is coupled to a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program from the memory, so that a device equipped with the chip system executes a method in any possible implementation of the first to third aspects above.
[0073] The chip may include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.
[0074] In the eleventh aspect, a computer program product is provided, comprising: a computer program code, which, when executed by a device, enables the device to execute the method in any possible implementation of the first to third aspects above. BRIEF DESCRIPTION OF THE DRAWINGS
[0075] FIG1 is a schematic diagram of a communication system 100 provided in an embodiment of the present application.
[0076] FIG2 is a schematic diagram of the architecture of an access network device provided in an embodiment of the present application.
[0077] FIG3 is a schematic diagram of an AI application framework provided in an embodiment of the present application.
[0078] FIG4 is a flow chart of a communication method 400 provided in an embodiment of the present application.
[0079] FIG5 is a flow chart of a communication method 500 provided in an embodiment of the present application.
[0080] FIG6 is a schematic block diagram of a communication device 1000 provided in an embodiment of the present application.
[0081] FIG7 is a schematic block diagram of a communication device 2000 provided in an embodiment of the present application.
[0082] FIG8 is a schematic block diagram of a chip system 3000 provided in an embodiment of the present application. DETAILED DESCRIPTION
[0083] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.
[0084] FIG1 is a schematic diagram of a communication system 100 provided in an embodiment of the present application. As shown in FIG1 , the communication system 100 includes an access network device 10, a terminal device 20, and a network management network element 30. In this communication system, the terminal device 20 can send uplink data / signals / information to the access network device 10, and the access network device 10 can send downlink data / signals / information to the terminal device 20. Optionally, data / signals / information can be transmitted between the access network device 10 and the network management network element 30. Optionally, data / signals / information can be transmitted between the terminal device 20 and the network management network element 30.
[0085] The communication method provided in the embodiment of the present application may also involve devices or transmission nodes not shown in Figure 1, and the embodiment of the present application is not limited to this.
[0086] The above-mentioned communication system applied to the embodiment of the present application is only an example. The communication system applicable to the embodiment of the present application is not limited to this. Any communication system that can realize the functions of the above-mentioned devices is applicable to the embodiment of the present application.
[0087] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: long term evolution (LTE) system, advanced long term evolution (LTE-A) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), NR system and other fifth generation (5G) systems, or future evolved communication systems (for example, 6G mobile communication system). The technical solutions of the embodiments of the present application can be applied to various scenarios such as vehicle-to-everything (V2X), Internet of Vehicles, machine type communication (MTC), Internet of Things (IoT), long term evolution-machine (LTE-M), machine to machine (M2M), etc.
[0088] The terminal device can be a wireless terminal device that can receive access network device scheduling and instruction information. The terminal device can be a device that provides voice and / or data connectivity to the user, a handheld device with wireless connection function, or other processing device connected to a wireless modem.
[0089] The terminal device in the embodiment of the present application may also be referred to as a terminal, an access terminal, a user unit, a user equipment (UE), a subscriber unit (SU), a subscriber station (SS), a user station, a mobile station (MB), a mobile station (mobile), a remote station (RS), an access point (AP), a remote terminal (RT), an access terminal (AT), a user terminal (UT), and a user agent (UA). The terminal device is a device that includes a wireless communication function (providing voice / data connectivity to the user). For example, a handheld device with a wireless connection function, or a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a train, an airplane, a mobile Internet device (MID), a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control (such as a robot, etc.), a wireless terminal in the Internet of Vehicles (such as a vehicle-mounted device, a whole vehicle equipment, a vehicle-mounted module, a vehicle, etc.), a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a personal communication service (PCS) phone, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a wearable device, etc. In addition, the terminal device can also be used in scenarios such as unmanned driving, telemedicine, smart grid, transportation safety, smart city, smart city, smart home, etc.
[0090] The network device in the embodiment of the present application may be an access network device, which may also be referred to as a radio access network (RAN) device or a RAN node, wherein the RAN may be connected to the core network, including but not limited to: various base stations, such as the next generation Node B (gNodeB, gNB), evolved Node B (eNB) or base station equipment in future evolved communication systems, or a server, a wearable device, an in-vehicle device, a wireless relay node, a wireless backhaul node, a transmission point (TP) or a transmission and reception point (TRP), etc., or one or a group (including multiple antenna panels) of antenna panels of a base station, or a network node constituting a base station, such as a baseband unit (BBU), a centralized unit (CU) or a distributed unit (DU), etc. The base station may be a macro base station, a micro base station, a pico base station, a small station, a relay station or a balloon station, etc.
[0091] The network management element in the embodiment of the present application can be a network element that registers the AI model.
[0092] Exemplarily, the network management network element may be a core network (CN) device, and the core network device may include one or more core network elements. Taking the 5G core network as an example, the 5G core network includes an access and mobility management function (AMF) network element responsible for services such as mobility management and access management, a session management function (SMF) network element responsible for session management, a user plane function (UPF) network element responsible for data packet routing and forwarding and quality of service (QoS) control on the user plane, and a policy control function (PCF) network element. The above-mentioned core network elements can work independently or be combined to implement certain control functions. For example, AMF, SMF, and PCF can be combined together as a core network device.
[0093] Exemplarily, the network management network element can be an operations, administration and maintenance (OAM) entity. OAM can divide the management work of the network into three categories: operation, administration, and maintenance. Operation mainly completes the analysis, prediction, planning and configuration work of daily network and business; maintenance mainly involves daily operational activities such as testing and fault management of the network and its services. Exemplarily, in this solution, OAM can store and manage AI models / model identifiers, as well as receive model registration requests sent by the first access network device and make decisions.
[0094] For example, the network management element can be an upper-layer entity OTT (over the top). OTT is independent of the 3GPP network element. Its main functions in this solution are to store and manage AI models / model IDs, receive model registration requests from 3GPP network elements, and make decisions on these registration requests.
[0095] Exemplarily, the network management element may also be a third-party node. The third-party node may be, for example, a third-party application service platform, where a third party other than the operator utilizes the operator's network to provide services to users.
[0096] It can be understood that all or part of the functions of the network device or terminal device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).
[0097] Figure 2 is a schematic diagram of the architecture of an access network device provided in an embodiment of the present application. As shown in Figure 2, the access network device involved in the embodiment of the present application can adopt a separate architecture including a CU and a DU. The CU and the DU can be understood as a division of the access network device from a logical functional perspective. The CU and the DU can be physically separated or deployed together. Multiple DUs can share one CU. A DU can also be connected to multiple CUs (not shown in Figure 2). The CU and the DU can be connected through an interface, such as an F1 interface. The CU and the DU can be divided according to the protocol layer of the wireless network. One possible division method is: the CU is used to perform the functions of the radio resource control (RRC) layer, the service data adaptation protocol (SDAP) layer, and the packet data convergence protocol (PDCP) layer, and the DU is used to perform the functions of the radio link control (RLC) layer, the media access control (MAC) layer, the physical layer, etc.
[0098] It is understood that the division of the processing functions of the CU and DU according to the protocol layer is only an example, and the CU and DU may also be divided in other ways. For example, the CU or DU may be divided into functions of more protocol layers than the above division method. For example, the CU or DU may also be divided into some processing functions of the protocol layer in the above division method.
[0099] In one design, the functions of the CU or DU can be divided according to service type or other system requirements. For example, by latency, functions whose processing time meets the latency requirement are implemented in the DU, while functions that do not meet the latency requirement are implemented in the CU.
[0100] In another design, a CU can also have one or more core network functions. One or more CUs can be centrally located or separately located. For example, a CU can be located on the network side for centralized management. A DU can have multiple radio frequency functions, or the radio frequency functions can be remotely located.
[0101] The functions of a CU can be implemented by a single entity or by different entities. For example, the functions of a CU can be further divided, such as separating the control plane (CP) and the user plane (UP), namely the CU control plane (CU-CP) and the CU user plane (CU-UP). The CU control plane CU-CP also includes a further divided architecture, that is, the CU-CP is further divided into CU-CP1 and CU-CP2. CU-CP1 includes various radio resource management functions, while CU-CP2 only includes RRC functions and PDCP-C functions (i.e., the basic functions of control plane signaling at the PDCP layer).
[0102] In different systems, CU (including CU-CP or CU-UP) or DU may have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (O-RAN) system, CU may also be referred to as O-CU (open CU), DU may also be referred to as O-DU, CU-CP may also be referred to as O-CU-CP, and CU-UP may also be referred to as O-CU-UP. For the convenience of description, this application uses CU, CU-CP, CU-UP, and DU as examples for description.
[0103] The AI module is a module with machine learning computing capabilities. In a wireless communication system, the AI module can be located in the OAM, or in the access network device (for example, if the access network device is a separated architecture, it can be located in the CU), in the terminal device, or as a separate network element entity AI control layer (AI control layer, AIC). If the O-RAN architecture is adopted, the AI module can also be set in the RAN intelligent controller (RAN intelligent controller, RIC), and the RIC can obtain network side and / or terminal side information from the access network device and / or terminal device for AI model training or reasoning, and the training or reasoning results can be transmitted to the RAN node and / or terminal device.
[0104] The AI module's primary function in wireless communication systems is to perform a series of AI calculations, including model building, training approximation, and reinforcement learning, based on input data. This input data can include network operation data provided by access network equipment or monitored by OAM, such as network load and channel quality, or user-plane data transmission information provided by the core network. The trained model provided by the AI module predicts network changes on the RAN side and can be used for load forecasting and terminal device path prediction. Furthermore, based on the trained model's predictions of RAN network performance, the AI module can perform policy inference from perspectives such as network energy conservation and mobility optimization, ultimately developing effective and efficient energy conservation and mobility optimization strategies.
[0105] When the AI model is located in the CU and the CU's CP and UP are separated, the CP can be responsible for receiving the AI model and subsequent AI reasoning and policy generation functions. When the CU-CP is further divided into CU-CP1 and CU-CP2, CU-CP1 can be responsible for receiving the AI model and subsequent AI model reasoning functions, and generating specific interaction signaling, which is then sent by CU-CP2.
[0106] Figure 3 is a schematic diagram of an AI application framework provided by an embodiment of the present application. As shown in Figure 3, the AI application framework includes a data acquisition module, a model training module, a model reasoning module, and an execution entity (Actor).
[0107] The model training module and model inference module are examples of AI modules. For example, network devices and terminal devices shown in Figure 1, CUs and DUs shown in Figure 2, or other management entities can input data into the data acquisition module, which can serve as a database for AI model training and data analysis and inference. The model training module analyzes the training data output by the data acquisition module and generates a usable AI model, which is then deployed to the model inference module. Based on the inference data output by the data acquisition module, the model inference module generates reasonable predictions about network operation based on the AI model and feeds the AI model's performance data back to the model training module. The model training module then continues training the model based on the fed-back performance data and informs the model inference module of the updated AI model. Alternatively, the model inference module guides network policy adjustments based on the inference data and AI model output by the data acquisition module. These policy adjustments are centrally planned by the execution entity and sent to multiple network entities for execution. Furthermore, the specific network performance after the relevant policies are applied is fed back to the data acquisition module for storage.
[0108] 3GPP has introduced multiple AI application scenarios on the RAN side. In some of these scenarios, the terminal device can implement some AI functions, and the access network device can transmit the AI model to the terminal device. Additionally, in some AI application scenarios on the terminal device side, the access network device can implement some AI functions, and the terminal device can transmit the AI model to the access network device.
[0109] AI applications on the RAN include, but are not limited to, the following scenarios: energy saving, load balancing, mobility optimization, channel state information-reference signal (CSI-RS) feedback enhancements, beam management enhancements (BME), and positioning accuracy enhancements (PAE). These scenarios are also referred to as AI use cases.
[0110] In the aforementioned AI use cases, all or part of the AI functionality can be implemented by the terminal device. If the AI model is trained by the access network device, the access network device can send the AI model to the terminal device. To ensure the legal authorization of the trained model and a unified understanding of the model between the UE and the access network device, an AI model registration process needs to be designed.
[0111] The embodiments of the present application provide a communication method and apparatus, which registers an AI model trained by an access network device to a CN device or an OAM network element and makes the registration-related information consistent between the access network device and the terminal device, so that the terminal device and the access network device have a unified understanding of the AI model, thereby improving the use effect of the AI model in AI application scenarios.
[0112] To facilitate understanding of the embodiments of the present application, the following points are explained:
[0113] First, in this application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments based on their internal logical relationships.
[0114] It can be understood that some optional features in the embodiments of the present application may not depend on other features in certain scenarios, and may also be combined with other features in certain scenarios, without limitation.
[0115] It can be understood that the solutions in the various embodiments of the present application can be used in combination, and the explanations or descriptions of the various terms, similar operations or steps appearing in the embodiments can be referenced or explained with each other in the various embodiments, and the present application does not limit this.
[0116] Second, in this application, "at least one" means one or more, and "more" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In the text description of this application, the character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can mean: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c. Wherein a, b and c can be single or multiple, respectively.
[0117] Third, throughout this application, the terms "first," "second," and various numerical references are used for descriptive purposes only and are not intended to limit the scope of the embodiments of this application. For example, they are used to distinguish between different messages, rather than to describe a specific order or precedence. It should be understood that these references are interchangeable, where appropriate, to allow for the description of scenarios beyond the embodiments of this application.
[0118] Fourth, in this application, the terms "comprise" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or are inherent to these processes, methods, products or apparatuses.
[0119] Fifth, in this application, "used to indicate" can include being used for direct indication and being used for indirect indication. When describing that a certain indication information is used to indicate A, it can include that the indication information directly indicates A or indirectly indicates A, and does not necessarily mean that the indication information carries A.
[0120] Sixth, in this application, "sending information to XX (device)" can be understood as the destination of the information being the device. This can include sending information to the device directly or indirectly. "Receiving information from XX (device) or receiving information from XX (device)" can be understood as the source of the information being the device, which can include receiving information from the device directly or indirectly. The information may undergo necessary processing between the source and destination, such as format changes, but the destination can still understand the valid information from the source.
[0121] The communication method provided by the embodiment of the present application will be described in detail below with reference to the accompanying drawings. The embodiment provided by the present application can be applied to any communication scenario in which a transmitting device and a receiving device communicate, such as the communication system shown in FIG1 above.
[0122] It should be noted that, as an example, the model involved in the embodiments of the present application may be an AI model.
[0123] Figure 4 is a flow chart of a communication method 400 provided in an embodiment of the present application. The target scenario of the scheme is that the AI model is trained on the first network device side, and the first network device sends the trained AI model to the terminal device. The method flow can be executed by the terminal device, the first network device, and the second network device, or by modules and / or devices (for example, chips or integrated circuits, etc.) with corresponding functions installed in the terminal device, the first network device, and the second network device, which is not limited by the present application. The following description is based on the terminal device, the first network device, and the second network device as the execution subjects, including the following steps.
[0124] S410: A first network device is trained to obtain a first model.
[0125] Among them, the first network device determines the AI model to be trained.
[0126] Exemplarily, the first network device determines the model training requirements and collects data, and confirms the AI model to be trained based on the model training requirements and the collected data. The first network device determines the model training requirements based on its own analysis of AI application scenarios and requirements, and the data collected by the first network device may include terminal device capabilities and measurement data used for model training.
[0127] Among them, the training requirements can be based on one or more of the following factors. For example, the first network device determines the scenario in which the AI model will be applied based on the current performance optimization requirements, such as throughput improvement, UE access rate improvement, etc.; it can also be the current ability of the terminal device and the first network device to apply AI, such as hardware capabilities, model support capabilities, etc.; it can also be other network nodes, such as OAM, etc., indicating training requirements to the first network device.
[0128] After determining the AI model to be trained, the first network device collects data for training the model and trains to obtain the first model.
[0129] Furthermore, after the first model is generated, auxiliary information (meta information) of the first model may also be generated, and the meta information may be used to describe the model.
[0130] Exemplarily, the meta information may include at least one of the following: model input information, model output information, model corresponding version number, model format, model requirements for device capabilities, model applicable manufacturer identifier, model manufacturer identifier, model applicable scenarios, model use case, scenario-related configuration, scenario-corresponding cell / base station-related configuration, model calculation complexity (e.g., the number of parameters used by the model, the number of operations during model use, etc.), model processing capability requirements, model data volume range, model performance, and model functionality. The model in the above meta information refers to the model corresponding to the meta information. For example, the meta information of the first model describes the first model.
[0131] In one implementation, the model version number may be the version number corresponding to the model used this time; the model format may be the compilation format of the model; the model's requirements for terminal device capabilities may be the computing power, storage capacity, etc. that the terminal device can provide; the model identifier to which the model can be applied may be the network equipment vendor identifier, terminal identifier, etc. to which the model can be applied; the manufacturer identifier of the model manufacturer may be the identifier of the manufacturer that owns the model; the performance of the model may include: model accuracy, model deviation, model deviation variance, model operation rate, etc.; the use case of the model may be the use case of the target application of the model. For example, the use case of the model may include energy saving, load balancing, mobility optimization, channel state information-reference signal (CSI-RS) feedback enhancements (feedback enhancements), beam management enhancements (BME), and positioning accuracy enhancements (PAE); the scenario in which the model can be used may include that the model can be used in a specific cell, a cell network with a specific topology, or under a specific channel quality.
[0132] It is understood that the specific content of the above meta information may vary for different use cases. For example, when the first model is used for beam management enhancement, the input information may be the signal received power of the beam with existing measurement results, and the output information may be the predicted signal received power of the beam; when the first model is used for CSI-RS feedback enhancements, the input information in the meta information may be the historical CSI measurement results, and the output information may be the CSI measurement results predicted by the model.
[0133] The first network device in this application may be different specific devices in different use cases.
[0134] Exemplarily, the first network device may be an access network device in CSI-RS feedback enhancement and beam management enhancement, or the first network device may be a location management function (LMF) node in positioning enhancement, or the first network device may also be other third-party nodes. Exemplarily, other third-party nodes may be RIC or AIC, that is, the RIC or AIC node determines the model registration information and executes the registration application process to the control and management network element.
[0135] In the present application, the first network device can be a network device under a non-spilt architecture or a network device under a spilt architecture. When the first network device is a network device under a spilt architecture, the first network device includes a CU and a DU. For the CU and DU, refer to the description in Figure 2 and are not described in detail here. In step S410, the CU and DU can be trained to obtain the first model respectively. For the specific training acquisition method, refer to the above description of the first network device training to obtain the first model, which is not described in detail here.
[0136] It should be understood that the first model in this application generally refers to a model that has been trained or is about to be trained on the first network device and has not yet been registered.
[0137] S420: The first network device sends a first request message to the second network device. The first request message is used to request registration of the first model. The first request message includes a first identifier, and the first identifier corresponds to the first model.
[0138] Exemplarily, the first identifier includes a model identifier (identity, ID) of the first model. The model identifier may include a globally unique identifier for indicating the model, or it may be a unique identifier for indicating the model within the network provided by an operator. Specifically, the first identifier may be one or more specific bit streams, used to correspond to one or more model identifiers, and the number of bits of the bit stream is not limited; it may also be a range of bit stream numbers, for example, the first identifier may be a bit stream with serial numbers 1-4, used to correspond to one or more model identifiers. The model identifier may be a bit stream uniformly allocated globally, or it may be a bit stream allocated to each operator, or it may be a bit stream uniformly allocated globally to operators and then allocated by the operators. In terms of the content of the model identifier, the model identifier may be a bit stream without special information meaning, or it may be a bit stream that includes the operator's identification information, PLMN, all or part of the meta information, and at least one item in the cell list of the model corresponding to this model identifier.
[0139] In one implementation, the first request information may further include at least one of the following: meta information of the first model, a list of terminal devices that can use the first model, a list of cells that can use the first model, a list of public land mobile networks (PLMNs) that can use the first model, an expected time to use the first model, an index for indicating the first model, and a mapping relationship for mapping the first model. For the meta information, refer to the relevant description in S410 and are not described in detail here. The index for indicating the first model refers to the use of a shorter information than the first identifier to indicate the first identifier or the first model. Exemplarily, the index may include part of the content in the model identifier. It should be noted that the first identifier and the index are different information. The first identifier is an identifier that can uniquely indicate the first model within the global or operator coverage area, while the index is only generated by the first network device to more conveniently indicate the first identifier or the first model. After leaving the coverage area of the first network device, other access network devices may not be able to determine the first identifier or the first model through the index. The mapping relationship for mapping the first model refers to mapping the first identifier or the first model into a shorter bit stream. The index and mapping relationship can be used as a simple way to indicate the first model when the first network device and the second network device subsequently interact with the first model.
[0140] Exemplarily, the index used to indicate the first model and the mapping relationship used to map the first model can be used for subsequent interaction between the first network device and the second network device. Exemplarily, the interaction between the first network device and the second network device may include activation or deactivation or switching or fallback of the first model between the first network device and the second network device, where fallback refers to turning off the AI function from turning on the AI function. Since the number of bits of the model identifier is relatively long, the signaling overhead can be reduced by using a shorter index or mapping relationship to indicate the first model.
[0141] It should be understood that for the sake of ease of description, this application takes the first model as an example. In fact, the first network device can register multiple models. The multiple models can be indicated to the second network device for registration by the same request information, or each model can be indicated to the second network device for registration separately through a request information. This application does not limit this. The information corresponding to each model in the request information is similar to the information corresponding to the first model in the above-mentioned first request information, and will not be repeated here.
[0142] In step S420 , if the first network device is a network device under the spilt architecture, the CU integrates the information of the model to be registered on the CU and the DU, generates first request information, and sends the first request information to the second network device by the CU.
[0143] In one implementation, the first request information generated by the CU may also include a unit identifier, which may identify the CU or DU of the model corresponding to the model identifier in the training first request information. The training here may refer to completed training, ongoing training, or about to be trained.
[0144] In the present application, the first model is registered at the second network device. Exemplarily, the second network device may be a core network device or an OAM.
[0145] It should be understood that there is no order between step S420 and step S410, that is, the first network device may initiate registration with the second network device after completing model training, or the first network device may initiate registration with the second network device after confirming the training requirements of the model and before completing model training on the first network device.
[0146] In one implementation, before S420 , the method further includes S430 .
[0147] S430: The first network device obtains first information and assigns a first identifier to the first model based on the first information, wherein the first information includes at least one model identifier that can be registered by the first network device.
[0148] Specifically, the first network device can obtain the first information online. For example, the first network device receives the first information from the second network device. The first network device can also obtain the first information offline. For example, the first network device is pre-configured with the first information or the first network device is pre-set with the first information when it leaves the factory. The first network device can also obtain the first information by itself. For example, the first network device can randomly generate the first information or generate the first information based on the training requirements of the model and the collected data.
[0149] The model identifier in the first information is the model identifier of the model that the first network device can use for registration, and can also be called a preset identifier. For the preset identifier, please refer to the description of the model identifier in S420 and will not be repeated here. In addition, the preset identifier can be distinguished according to the cell managed by the first network device. For example, if the first network device manages cell 1 and cell 2, cell 1 can use ID #1 and cell 2 can use ID #2.
[0150] Optionally, the first information may also include first relevant information of the model corresponding to the preset identifier. For example, the first relevant information may include at least one of the following: meta information of the model corresponding to the preset identifier, cell information that can use the model corresponding to the preset identifier, information on the effective time of the model corresponding to the preset identifier, and terminal device information that can use the model corresponding to the preset identifier.
[0151] Among them, the cell information of the model that can use the preset identifier may include at least one of the following information: cell global identifier (CGI), physical cell identifier (PCI) and frequency, cell identifier (cell ID), non-public network identifier (NPN ID), non-terrestrial network identifier (NTN ID), tracking area code (TAC), public land mobile network (PLMN) or identification information of the network device to which the cell belongs (such as a global network device identifier), wherein the non-public network identifier can include the CAG ID of the PNI-NPN and / or the NID of the SNPN.
[0152] The above-mentioned meta information can be found in the relevant description in S410 and will not be elaborated here. However, it should be understood that the specific content included in the meta information in S430 may not be exactly the same as that included in the meta information in S410 or S420. For example, the meta information in S430 includes the input information of the model, the output information of the model, the version number corresponding to the model, and the format of the model. The meta information in S410 includes the complexity of the model calculation, the model processing capability requirements, the range of the model data volume, and the format of the model.
[0153] After obtaining the first information, the first network device selects a model identifier from the preset identifiers in the first information and assigns it to the first model. Exemplarily, if the first information includes meta information of the model corresponding to the preset identifier, and the first network device has obtained the meta information of the first model, the first network device may pair the meta information of the model corresponding to the preset identifier with the meta information of the first model. If the meta information of the model corresponding to the preset identifier is partially or completely identical to the meta information of the first model, the preset identifier is used as the first identifier of the first model. The first network device may also randomly select a preset identifier from the preset identifiers as the model identifier of the first model, i.e., randomly select the first identifier.
[0154] For example, when the first network device is a network device under the spilt architecture, the CU and / or DU can obtain a preset identifier. Furthermore, the CU and / or DU may also obtain the first relevant information of the model corresponding to the preset identifier. For the specific acquisition method and the specific content of the preset identifier and the first relevant information of the model corresponding to the preset identifier, please refer to the above description of the first network device obtaining the first information, which will not be repeated here.
[0155] After the DU and CU have confirmed their respective model training requirements, an interaction regarding model identifier allocation is performed. Exemplarily, the interaction process may be that the CU sends a REQUEST message to the DU to initiate the interaction regarding model identifier allocation, i.e., the CU requests information regarding model identifier allocation on the DU via the REQUEST message. Alternatively, the DU may proactively initiate the interaction regarding model identifier allocation, i.e., the DU proactively sends information regarding model identifier allocation on the DU to the CU. This application does not impose any restrictions on this.
[0156] Specifically, when the DU has obtained a preset identifier, the CU obtains the information of the preset identifier that the DU has obtained. Further, if the DU has also obtained the first relevant information of the model corresponding to the preset identifier, the CU can also obtain the first relevant information of the model corresponding to the preset identifier that the DU has obtained. The CU can actively obtain the above information from the DU, for example, the CU periodically obtains the above information from the DU; the CU can also obtain the above information from the DU after receiving the corresponding indication information. This application does not limit the source of the indication information; or the DU can even actively indicate the above information to the CU.
[0157] Optionally, the DU may also indicate to the CU a model identifier that the DU may provide to other DUs or CUs.
[0158] Optionally, the DU may further indicate to the CU whether more model identifiers are needed. Furthermore, the DU may further indicate to the CU the specific model identifiers needed.
[0159] After obtaining the above information, the CU can integrate the preset identifiers obtained by all DUs, assign a model identifier to each DU, and send the corresponding model identifier to each DU. Furthermore, if the above information obtained by the CU includes the first relevant information of the model corresponding to the preset identifier, the content integrated by the CU and sent to the DU may also include the first relevant information of the model corresponding to the preset identifier.
[0160] If the DU does not obtain the preset identifier, the CU obtains the DU's demand information, which may include at least one of the following: the number of model identifiers required by the DU, the model identifier required by the DU, and first relevant information about the model corresponding to the model identifier required by the DU. The DU's demand information obtained by the CU may be actively requested by the CU to the DU, for example, the CU sends a request to the DU requesting the DU to periodically send the above-mentioned demand information; the DU's demand information obtained by the CU may also be actively indicated by the DU to the CU, for example, the DU actively and periodically sends the above-mentioned demand information to the CU.
[0161] After obtaining the demand information of the DU, the CU may integrate the demand information of all DUs and assign the preset identifier on the CU to each DU. Furthermore, the CU may also send the first relevant information of the model corresponding to the preset identifier to each DU.
[0162] Furthermore, in a network device in a split architecture, a CU may correspond to multiple DUs. If some of the multiple DUs have obtained preset identifiers and some have not, the CU may integrate the preset identifiers obtained by all DUs and the demand information of all DUs to obtain a model identifier that can be assigned to each DU and send it to each DU. Furthermore, if the CU also obtains the first relevant information of the model corresponding to the preset identifier on the DU, the content integrated by the CU and sent to the DU may also include the first relevant information of the model corresponding to the preset identifier. Exemplarily, the CU may obtain the model identifier assigned to each DU based on one or more factors, such as ensuring that the DU obtains sufficient model identifiers, avoiding one model corresponding to multiple model identifiers, and avoiding multiple DUs requiring the same model identifier.
[0163] For example, if the DU indicates to the CU that more model identifiers are needed, the CU may allocate other model identifiers that other DUs or the CU itself can provide to the DU.
[0164] For example, if multiple DUs indicate to the CU that they need the same model identifier, the centralized unit may assign the model identifier to one of the DUs and indicate to the other DUs that the model identifier has been assigned.
[0165] For example, if the DU indicates different model identifiers for the same model, the CU may unify the model identifier of the model.
[0166] By interacting with CU and DU regarding the requirements for preset model identification and integrating them by CU, the requirements for corresponding model identification of different DUs in the split architecture can be balanced.
[0167] It should be noted that there is no strict order between step S430 and step S410, that is, the first network device may assign a model identifier to the model from the preset identifier after completing the model training, or the first network device may assign a model identifier to the model being trained or to be trained from the preset identifier after confirming the model training requirements.
[0168] S440: The second network device registers the first model.
[0169] Specifically, after the second network device receives the registration information sent by the first network device (i.e., the first request information in S420 of this application), the second network device can determine whether the registration information is valid. If the second network device approves the registration result corresponding to the registration information, the model registration is successful; if the second network device does not approve the registration result corresponding to the registration information, the model registration fails.
[0170] In one implementation, the second network device may determine whether to approve the registration information based on preset conditions. For example, if the number of model identifiers applied for registration by the first network device exceeds the number approved by the second network device, or if one or more items of the meta information of the model applied for registration by the first network device do not meet the requirements of the second network device, the second network device will not approve the registration information.
[0171] S450: The second network device feeds back the registration result of the first model to the first network device.
[0172] After receiving the first request information sent by the first network device, the second network device may determine whether to accept the request and feed back a registration result to the first network device.
[0173] Specifically, if the second network device accepts the request, the second network device may feedback to the first network device that the registration is accepted or the registration is successful. The feedback may be explicit or implicit.
[0174] Exemplarily, the second network device may explicitly feedback registration success or registration acceptance by sending ACK information to the first network device.
[0175] Exemplarily, the second network device may also implicitly indicate successful registration or acceptance of registration by not sending feedback information to the first network device. Accordingly, the first network device includes a timer, and the first network device starts the timer after sending the first request information. If no feedback information is received from the second network device within the first time period, the first network device determines that the first model is successfully registered or the second network device has accepted the registration of the first model.
[0176] For feedback that the second network device accepts the registration or that the registration is successful, the first network device may execute step S470. If the first network device is a network device in a spilt architecture, the CU may obtain the registration result and send the registration result, i.e., the model identifier and / or the first related information, to each DU accordingly.
[0177] If the second network device does not accept the request, the second network device may feedback to the first network device that the registration is not accepted or the registration fails. Similarly, the feedback may be explicit or implicit.
[0178] Exemplarily, the second network device may explicitly feedback the registration failure or reject the registration by sending a Failure message to the first network device.
[0179] Furthermore, the second network device may further indicate the reason for rejecting the registration in the Failure message. For example, the second network device determines, based on the meta information included in the first request message, that the first model does not meet the requirements of the second network device, and thus provides feedback to the first network device that the reason for rejecting the registration is that the first model does not meet the requirements of the second network device.
[0180] Exemplarily, the second network device may also implicitly indicate that the registration has failed or that the registration is not accepted by not sending feedback information to the first network device. Accordingly, the first network device includes a timer, and the first network device starts the timer after sending the first request information. If no feedback information is received from the second network device within the second time period, the first network device determines that the registration of the first model has failed or the second network device does not accept the registration of the first model.
[0181] For feedback that the second network device does not accept the registration, the first network device may execute step S460.
[0182] S460: The first network device re-modifies the training requirements of the first model and sends a second request message based on the modified training requirements. The specific content of the second request message refers to the description of the first request message and is not repeated here.
[0183] For example, if the second network device does not recognize the input information and output information in the first model registration information, the first network device modifies the model training method according to the reasons fed back by the second network device, so that the input information and output information of the trained model meet the requirements of the second network device; for example, if the second network device does not recognize the accuracy in the first model registration information, the first network device changes the model architecture, parameters or retrains according to the reasons fed back by the second network device, so that the accuracy of the trained model meets the requirements of the second network device.
[0184] It should be understood that in the present application, if the second request information sent in S460 is still not accepted by the second network device, the training requirements of the first model will continue to be modified until the second network device accepts the registration.
[0185] In the case where the first network device is a network device in a spilt architecture, after obtaining the registration result, the CU can choose to re-interact with the DU, re-modify the training requirements of the model, generate and re-send the second request information to the second network device. For the specific interaction, please refer to the description in S430 and will not be repeated here. The content of the re-interaction between the CU and the DU may include the reason for the registration failure and the reallocation of the preset identifier.
[0186] In one embodiment, S470 is executed after the second network device accepts the registration.
[0187] S470: The first network device sends second information to the terminal device, where the second information includes the first model.
[0188] In one implementation, the second information may further include at least one of the following: a first identifier, information indicating that the first model has completed registration, meta information of the first model, an index corresponding to the first identifier, an index corresponding to the first identifier and an applicable cell range, a mapping rule corresponding to the first identifier, a mapping rule corresponding to the first identifier and an applicable cell range, wherein the cell range may be represented by a CGI list. By using information such as the index / mapping relationship corresponding to the interaction model between the first network device and the terminal device, the need to send a complete model identifier when subsequently indicating the model is avoided, thereby reducing signaling overhead.
[0189] If the first network device is a network device in a spilt architecture, if the first model is a model trained and registered by the CU, it can be sent to the corresponding terminal device through the DU. If the first model is a model trained and registered by the DU, it can be sent directly to the terminal device, or the first model can be uploaded to the CU first, and then sent to the terminal device through the DU by the CU.
[0190] S480: The first network device and the terminal device perform model management.
[0191] Exemplarily, model management includes interactions such as activation / deactivation / rollback / switching of the model between the first network device and the terminal device.
[0192] In one implementation, the first network device and the terminal device perform model management on the first model based on the first identifier.
[0193] For example, after completing registration of the first model, if activation of the first model is required, the first network device may send an activation instruction to the terminal device, the activation instruction including a first identifier. After the terminal device recognizes the first identifier in the activation instruction, it may activate the first model. Optionally, the activation instruction includes a bit to indicate that an activation operation is to be performed on the model.
[0194] In one implementation, the first network device and the terminal device perform model management on the first model based on the index / mapping relationship in S470.
[0195] Exemplarily, after completing registration of the first model, if activation of the first model is required, the first network device may send an activation instruction to the terminal device, where the activation instruction includes an index of the first identifier or an identifier corresponding to the first identifier determined according to a mapping relationship. After the terminal device recognizes the index of the first identifier in the activation instruction or the identifier corresponding to the first identifier determined according to the mapping relationship, the first model may be activated. Optionally, the activation instruction may include a bit to indicate that an activation operation is to be performed on the model.
[0196] Based on the above solution, the first network device generates request information and completes the registration process with the second network device through its own judgment of model training and application, so that all devices involved in the application scenario of the first model, such as terminal devices, access network devices, and network management network elements within the coverage of the same operator, can have a unified understanding of the first model, including that after registration is completed, each device can use the first identifier to call the first model. Furthermore, when the terminal device moves to the coverage of other access network devices, it can still use the first identifier to call the first model, which facilitates subsequent detection and management of the first model, thereby improving the use effect of the AI model in various application scenarios.
[0197] Figure 5 is a flow chart of a communication method 500 provided in an embodiment of the present application. Unlike method 400, in which a first network device can communicate directly with a second network device, method 500 does not have a direct communication interface between the first and second network devices. Therefore, in method 500, communication between the first and second network devices must be forwarded through a terminal device. For example, in method 500, the first network device may be an access network device, and the second network device may be an OTT device. Method 500 includes the following steps, and the content described in method 400 is not repeated here.
[0198] S510: The first network device is trained to obtain a first model. For detailed description, see S410.
[0199] S520, the first network device sends indication information to the terminal device, wherein the indication information includes first request information. For a description of the first request information, see S420.
[0200] The indication information is used to instruct the terminal device to forward the first request information to the second network device.
[0201] Exemplarily, the indication information includes an identifier of the second network device.
[0202] In one implementation, before S520 , the method further includes S530 .
[0203] S530: The first network device obtains first information and assigns a first identifier to the first model based on the first information. For detailed description, see S430.
[0204] S540: The terminal device sends a first request message to the second network device.
[0205] S550: The second network device registers the first model. For the specific registration process, please refer to the description in the standard and will not be described here.
[0206] S560: The second network device feeds back a registration result. For specific content and form of the registration result, please refer to the relevant description of S450.
[0207] Exemplarily, there are two ways of feedback: in one way, the second network device directly feeds back the registration result to the first network device. In one implementation, the second network device obtains an indication that the first request information corresponds to the first network device; in the second way, the second network device feeds back the registration result to the terminal device, and the terminal device forwards the registration result to the first network device.
[0208] If the first network device is a network device in a spilt architecture, the CU interacts with the terminal device or the second network device to obtain the registration result. After obtaining the registration result, the interaction between the CU and the DU is described in S450 and S460.
[0209] For feedback that the second network device does not accept the registration, the first network device may execute step S570.
[0210] At S570, the first network device modifies the training requirements of the first model and sends a second request message based on the modified training requirements. For details, see S460. For example, the first network device may send the second request message directly to the second network device, see S420, or may send the second request message to the second network device via a terminal device, see S520.
[0211] After the second network device accepts the registration, S580 is executed.
[0212] S580, the first network device sends second information to the terminal device, where the second information includes the first model. For details, see S470.
[0213] S590: The first network device and the terminal device perform model management. For details, see S480.
[0214] Based on the above solution, for the case where there is no direct interface between the first network device and the second network device, for example, the first network device is an access network device and the second network device is OTT, the first network device can send a first request message to the second network device through the terminal device, thereby realizing the registration of the first model.
[0215] It should be understood that the size of the serial numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0216] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.
[0217] It should also be understood that in some of the above embodiments, devices in existing network architectures are mainly used as examples for illustrative purposes, and it should be understood that the embodiments of the present application do not limit the specific form of the devices. For example, devices that can achieve the same functions in the future are applicable to the embodiments of the present application.
[0218] It can be understood that in the above-mentioned method embodiments, the methods and operations implemented by devices (such as the above-mentioned terminal devices, first network devices, second network devices, etc.) can also be implemented by components of the devices (such as chips or circuits).
[0219] The method embodiment of the present application is described above in conjunction with the accompanying drawings. The device embodiment of the present application is described below. It can be understood that the description of the method embodiment and the description of the device embodiment can correspond to each other. Therefore, for parts not described, reference can be made to the previous method embodiment.
[0220] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the interaction between various network elements. It can be understood that each network element, such as a transmitting end device or a receiving end device, includes a hardware structure and / or software module corresponding to the execution of each function in order to implement the above functions. Those skilled in the art should be aware that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0221] In the embodiment of the present application, the functional modules of the transmitting device or the receiving device can be divided according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation. The following is an example of dividing each functional module according to each function.
[0222] Figure 6 is a schematic block diagram of a communication device 1000 provided in an embodiment of the present application. As shown in Figure 6, the device 1000 may include a transceiver unit 1010 and a processing unit 1020. The transceiver unit 1010 can communicate with the outside world, and the processing unit 1020 is used for data processing. The transceiver unit 1010 may also be referred to as a communication interface or a communication unit.
[0223] In one possible design, the device 1000 can implement steps or processes corresponding to those performed by the first network device in the above method embodiment, wherein the processing unit 1020 is used to perform processing-related operations of the first network device in the above method embodiment, and the transceiver unit 1010 is used to perform transceiver-related operations of the first network device in the above method embodiment.
[0224] In another possible design, the device 1000 can implement steps or processes corresponding to those executed by the terminal device in the above method embodiment, wherein the processing unit 1020 is used to execute processing-related operations of the terminal device in the above method embodiment, and the transceiver unit 1010 is used to execute transceiver-related operations of the terminal device in the above method embodiment.
[0225] In another possible design, the device 1000 can implement steps or processes corresponding to those performed by the second network device in the above method embodiment, wherein the processing unit 1020 is used to perform processing-related operations of the second network device in the above method embodiment, and the transceiver unit 1010 is used to perform transceiver-related operations of the second network device in the above method embodiment.
[0226] It should be understood that the device 1000 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merging logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device 1000 can be specifically the transmitting end in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the transmitting end in the above-mentioned method embodiment, or the device 1000 can be specifically the receiving end in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the receiving end in the above-mentioned method embodiment. To avoid repetition, it will not be described here.
[0227] The device 1000 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the sending end in the above-mentioned method, or the device 1000 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the receiving end in the above-mentioned method. The functions can be implemented by hardware, or the corresponding software can be implemented by hardware. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as the processing unit, can be replaced by a processor to respectively perform the transceiver operations and related processing operations in each method embodiment.
[0228] In addition, the above-mentioned transceiver unit can also be a transceiver circuit (for example, it can include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit. In an embodiment of the present application, the device in Figure 6 can be the receiving end or the transmitting end in the aforementioned embodiment, or it can be a chip or a chip system, such as a system on chip (SoC). Among them, the transceiver unit can be an input and output circuit or a communication interface. The processing unit is a processor or microprocessor or integrated circuit integrated on the chip. This is not limited here.
[0229] Figure 7 is a schematic block diagram of a communication device 2000 provided in an embodiment of the present application. As shown in Figure 7, the device 2000 includes a processor 2010 and a transceiver 2020. The processor 2010 and the transceiver 2020 communicate with each other via an internal connection path. The processor 2010 is configured to execute instructions to control the transceiver 2020 to transmit and / or receive signals.
[0230] Optionally, the apparatus 2000 may further include a memory 2030, which communicates with the processor 2010 and the transceiver 2020 via an internal connection path. The memory 2030 is used to store instructions, and the processor 2010 may execute the instructions stored in the memory 2030.
[0231] In a possible implementation, the apparatus 2000 is used to implement various processes and steps corresponding to the first network device in the above method embodiment.
[0232] In another possible implementation, the apparatus 2000 is used to implement the various processes and steps corresponding to the terminal device in the above method embodiment.
[0233] In yet another possible implementation, the apparatus 2000 is configured to implement the various processes and steps corresponding to the second network device in the above method embodiment.
[0234] It should be understood that device 2000 can specifically be the transmitting end or receiving end in the above-mentioned embodiments, or can also be a chip or chip system. Correspondingly, the transceiver 2020 can be the transceiver circuit of the chip, which is not limited here. Specifically, the device 2000 can be used to perform the various steps and / or processes corresponding to the transmitting end or receiving end in the above-mentioned method embodiments.
[0235] Optionally, the memory 2030 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information. The processor 2010 may be configured to execute instructions stored in the memory. When the processor 2010 executes the instructions stored in the memory, the processor 2010 is configured to perform the various steps and / or processes of the above-described method embodiments corresponding to the transmitting end or the receiving end.
[0236] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it will not be described in detail here.
[0237] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above-described method embodiment can be completed by hardware integrated logic circuits in the processor or by software instructions. The above-described processor can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The processor in the embodiments of the present application can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above-described method.
[0238] It will be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), etc. It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.
[0239] FIG8 is a schematic block diagram of a chip system 3000 according to an embodiment of the present application. As shown in FIG8 , the chip system 3000 (or also referred to as a processing system) includes a logic circuit 3010 and an input / output interface 3020 .
[0240] Logic circuit 3010 may be a processing circuit in chip system 3000. Logic circuit 3010 may be coupled to a storage unit and call instructions in the storage unit, so that chip system 3000 can implement the methods and functions of various embodiments of the present application. Input / output interface 3020 may be an input / output circuit in chip system 3000, outputting information processed by chip system 3000 or inputting data or signaling information to be processed into chip system 3000 for processing.
[0241] As a solution, the chip system 3000 is used to implement the operations performed by the terminal device in the above various method embodiments.
[0242] For example, the logic circuit 3010 is used to implement the processing-related operations performed by the terminal device in the above method embodiment, such as the processing-related operations performed by the terminal device in the embodiment shown in Figure 4 or Figure 5; the input / output interface 3020 is used to implement the sending and / or receiving-related operations performed by the terminal device in the above method embodiment, such as the sending and / or receiving-related operations performed by the terminal device in the embodiment shown in Figure 4 or Figure 5.
[0243] The present application also provides a computer-readable storage medium storing computer instructions for implementing all or part of the steps of the method executed by the terminal device or the first network device in each of the above method embodiments. The storage medium in this application includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk.
[0244] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computer, implement the methods performed by the terminal device and the first network device in the above-mentioned method embodiments.
[0245] An embodiment of the present application further provides a communication system, which includes the first network device, the terminal device, and the second network device in the above embodiments.
[0246] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.
[0247] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0248] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0249] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0250] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on practical needs to achieve the objectives of this embodiment.
[0251] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
Claims
1. A communication method, applied to a first network device, characterized in that: include: Train to obtain the first model; Sending a first request message, where the first request message is used to request registration of the first model, and the first request message includes a first identifier, and the first identifier corresponds to the first model.
2. The method according to claim 1, characterized in that The method further comprises: Acquire first information, where the first information includes at least one model identifier, and the at least one model identifier is a model identifier that can be registered by the first network device; The first identification is assigned to the first model based on the first information.
3. The method according to claim 2, characterized in that The obtaining of the first information comprises: receiving the first information from a second network device; or The first information is preconfigured in the first network device.
4. The method according to claim 2, characterized in that: The obtaining of the first information comprises: The first network device generates the first information.
5. The method according to any one of claims 2 to 4, characterized in that The first information also includes at least one of the following: Auxiliary information of the model corresponding to the at least one model identifier, cell information that can use the model corresponding to the at least one model identifier, information on the effective time of the model corresponding to the at least one model identifier, and terminal device information that can use the model corresponding to the at least one model identifier.
6. The method according to any one of claims 1 to 5, characterized in that The first request information further includes at least one of the following: Auxiliary information of the first model, a list of terminal devices that can use the first model, a list of cells that can use the first model, a list of public land mobile networks that can use the first model, an expected time of using the first model, an index used to indicate the first model, and a mapping relationship used to map the first model.
7. The method according to any one of claims 1 to 6, characterized in that The sending of the first request information includes: The first request information is sent to the second network device.
8. The method according to any one of claims 1 to 6, characterized in that The sending of the first request information includes: Send indication information to a terminal device, where the indication information includes the first request information, to instruct the terminal device to forward the first request information to the second network device.
9. The method according to claim 8, characterized in that The method further comprises: A registration result of the first model is received from the terminal device.
10. The method according to claim 7 or 8, characterized in that: The method further comprises: A registration result of the first model is received from the second network device.
11. The method according to claim 9 or 10, characterized in that: If the registration result is successful, the method further includes: Sending second information to a terminal device, where the second information includes the first model.
12. The method according to claim 11, characterized in that The second information also includes at least one of the following: The first identifier, indication information that the first model has completed registration, auxiliary information of the first model, the index corresponding to the first identifier, the index corresponding to the first identifier and the applicable cell range, the mapping rule corresponding to the first identifier, the mapping rule corresponding to the first identifier and the applicable cell range.
13. The method according to claim 9 or 10, characterized in that: If the registration result is registration failure, the method further includes: Send a second request message based on the modified training requirements of the first model.
14. The method according to any one of claims 1 to 13, characterized in that The first network device includes a centralized unit and a distributed unit, and the method further includes: the centralized unit allocates a model identifier to the distributed unit based on the model identifier already allocated on the distributed unit and / or the distributed unit's demand information for the model identifier and sends it to the distributed unit.
15. The method according to any one of claims 1 to 14, characterized in that The first request information also includes: A unit identifier, where the unit identifier is used to identify a centralized unit or a distributed unit for training the first model.
16. The method according to claim 11 or 12, characterized in that: The first network device includes a centralized unit and a distributed unit, and the method further includes: If the first model is a model trained by the centralized unit, the centralized unit sends the second information to the terminal device through the distributed unit; If the first model is a model trained by the distributed unit, the distributed unit sends the second information to the terminal device, or the distributed unit sends the first model to the centralized unit, and the centralized unit sends the second information to the terminal device through the distributed unit.
17. A communication method, applied to a terminal device, characterized in that: include: Receiving indication information from a first network device, the indication information including first request information, the indication information being used to instruct the terminal device to forward the first request information to a second network device, the first request information being used to request registration of a first model, the first request information including a first identifier, the first identifier corresponding to the first model, and the first model being a model trained by the first network device; Forward the first request information to the second network device.
18. The method according to claim 17, characterized in that The method further comprises: The registration result of the first model is received from the second network device and forwarded to the first network device.
19. The method according to claim 17 or 18, characterized in that The first request information further includes at least one of the following: Auxiliary information of the first model, a list of terminal devices that can use the first model, a list of cells that can use the first model, a list of public land mobile networks that can use the first model, an expected time of using the first model, an index used to indicate the first model, and a mapping relationship used to map the first model.
20. The method according to any one of claims 17 to 19, characterized in that The method further comprises: Second information is received from the first network device, the second information including the first model.
21. The method according to claim 20, characterized in that The second information also includes at least one of the following: The first identifier, indication information that the first model has completed registration, auxiliary information of the first model, the index corresponding to the first identifier, the index corresponding to the first identifier and the applicable cell range, the mapping rule corresponding to the first identifier, the mapping rule corresponding to the first identifier and the applicable cell range.
22. A communication method, applied to a second network device, characterized in that: include: Receive first request information, where the first request information is used to request registration of a first model, and the first request information includes a first identifier, where the first identifier corresponds to the first model, and the first model is a model trained by a first network device; The first model is registered based on the first request information.
23. The method according to claim 22, characterized in that The receiving first request information comprises: receiving the first request information from the first network device; or The first request information is received from a terminal device, where the first request information is sent by the terminal device after receiving indication information from the first network device, where the indication information includes the first request information.
24. The method according to claim 23, characterized in that The method further comprises: Sending a registration result of the first model to the first network device based on the first request information from the first network device; or The registration result of the first model is sent to the terminal device based on the first request information from the terminal device.
25. A communication device, characterized in that: The method comprises a module or a unit for executing the method according to any one of claims 1 to 16.
26. A communication device, characterized in that: The method comprises modules or units for executing the method according to any one of claims 17 to 21.
27. A communication device, characterized in that: The method comprises modules or units for executing the method according to any one of claims 22 to 24.
28. A communication device, characterized in that: The apparatus comprises a processor coupled to a memory, wherein the memory stores instructions, and when the instructions are executed by the processor, the processor performs the method according to any one of claims 1 to 16.
29. A communication device, characterized in that: The apparatus comprises a processor coupled to a memory, wherein the memory stores instructions, and when the instructions are executed by the processor, the processor performs the method according to any one of claims 17 to 21.
30. A communication device, characterized in that: The apparatus comprises a processor coupled to a memory, wherein the memory stores instructions, and when the instructions are executed by the processor, the processor performs the method according to any one of claims 22 to 24.
31. A communication system, characterized in that: The method comprises a first network device and a second network device, wherein the first network device is used to execute the method according to any one of claims 1 to 16, and the second network device is used to execute the method according to any one of claims 22 to 24.
32. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 16, or enables the computer to execute the method according to any one of claims 17 to 21, or enables the computer to execute the method according to any one of claims 22 to 24.
Citation Information
Patent Citations
Communication method and device
CN118945670A
Data processing method and device
CN113839797A
Communication method and device
CN114143799A
Management and control model training method, device and system
CN115146691A
Wireless communication system AI model registration method and device
CN115767570A
